Phenotypic Antimicrobial Susceptibility Testing with Deep Learning Video Microscopy

Hui Yu, Wenwen Jing, Rafael Iriya, Yunze Yang, Karan Syal, Manni Mo, Thomas Grys, Shelley E. Haydel, Shaopeng Wang, Nongjian Tao

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Timely determination of antimicrobial susceptibility for a bacterial infection enables precision prescription, shortens treatment time, and helps minimize the spread of antibiotic resistant infections. Current antimicrobial susceptibility testing (AST) methods often take several days and thus impede these clinical and health benefits. Here, we present an AST method by imaging freely moving bacterial cells in urine in real time and analyzing the videos with a deep learning algorithm. The deep learning algorithm determines if an antibiotic inhibits a bacterial cell by learning multiple phenotypic features of the cell without the need for defining and quantifying each feature. We apply the method to urinary tract infection, a common infection that affects millions of people, to determine the minimum inhibitory concentration of pathogens from both bacteria spiked urine and clinical infected urine samples for different antibiotics within 30 min and validate the results with the gold standard broth macrodilution method. The deep learning video microscopy-based AST holds great potential to contribute to the solution of increasing drug-resistant infections.

Original languageEnglish (US)
Pages (from-to)6314-6322
Number of pages9
JournalAnalytical Chemistry
Volume90
Issue number10
DOIs
StatePublished - May 15 2018

Fingerprint

Microscopic examination
Anti-Bacterial Agents
Learning algorithms
Testing
Pathogens
Bacteria
Health
Imaging techniques
Pharmaceutical Preparations
Deep learning

ASJC Scopus subject areas

  • Analytical Chemistry

Cite this

Yu, H., Jing, W., Iriya, R., Yang, Y., Syal, K., Mo, M., ... Tao, N. (2018). Phenotypic Antimicrobial Susceptibility Testing with Deep Learning Video Microscopy. Analytical Chemistry, 90(10), 6314-6322. https://doi.org/10.1021/acs.analchem.8b01128

Phenotypic Antimicrobial Susceptibility Testing with Deep Learning Video Microscopy. / Yu, Hui; Jing, Wenwen; Iriya, Rafael; Yang, Yunze; Syal, Karan; Mo, Manni; Grys, Thomas; Haydel, Shelley E.; Wang, Shaopeng; Tao, Nongjian.

In: Analytical Chemistry, Vol. 90, No. 10, 15.05.2018, p. 6314-6322.

Research output: Contribution to journalArticle

Yu, H, Jing, W, Iriya, R, Yang, Y, Syal, K, Mo, M, Grys, T, Haydel, SE, Wang, S & Tao, N 2018, 'Phenotypic Antimicrobial Susceptibility Testing with Deep Learning Video Microscopy', Analytical Chemistry, vol. 90, no. 10, pp. 6314-6322. https://doi.org/10.1021/acs.analchem.8b01128
Yu, Hui ; Jing, Wenwen ; Iriya, Rafael ; Yang, Yunze ; Syal, Karan ; Mo, Manni ; Grys, Thomas ; Haydel, Shelley E. ; Wang, Shaopeng ; Tao, Nongjian. / Phenotypic Antimicrobial Susceptibility Testing with Deep Learning Video Microscopy. In: Analytical Chemistry. 2018 ; Vol. 90, No. 10. pp. 6314-6322.
@article{32088989949c4105af55525ab52ac984,
title = "Phenotypic Antimicrobial Susceptibility Testing with Deep Learning Video Microscopy",
abstract = "Timely determination of antimicrobial susceptibility for a bacterial infection enables precision prescription, shortens treatment time, and helps minimize the spread of antibiotic resistant infections. Current antimicrobial susceptibility testing (AST) methods often take several days and thus impede these clinical and health benefits. Here, we present an AST method by imaging freely moving bacterial cells in urine in real time and analyzing the videos with a deep learning algorithm. The deep learning algorithm determines if an antibiotic inhibits a bacterial cell by learning multiple phenotypic features of the cell without the need for defining and quantifying each feature. We apply the method to urinary tract infection, a common infection that affects millions of people, to determine the minimum inhibitory concentration of pathogens from both bacteria spiked urine and clinical infected urine samples for different antibiotics within 30 min and validate the results with the gold standard broth macrodilution method. The deep learning video microscopy-based AST holds great potential to contribute to the solution of increasing drug-resistant infections.",
author = "Hui Yu and Wenwen Jing and Rafael Iriya and Yunze Yang and Karan Syal and Manni Mo and Thomas Grys and Haydel, {Shelley E.} and Shaopeng Wang and Nongjian Tao",
year = "2018",
month = "5",
day = "15",
doi = "10.1021/acs.analchem.8b01128",
language = "English (US)",
volume = "90",
pages = "6314--6322",
journal = "Analytical Chemistry",
issn = "0003-2700",
publisher = "American Chemical Society",
number = "10",

}

TY - JOUR

T1 - Phenotypic Antimicrobial Susceptibility Testing with Deep Learning Video Microscopy

AU - Yu, Hui

AU - Jing, Wenwen

AU - Iriya, Rafael

AU - Yang, Yunze

AU - Syal, Karan

AU - Mo, Manni

AU - Grys, Thomas

AU - Haydel, Shelley E.

AU - Wang, Shaopeng

AU - Tao, Nongjian

PY - 2018/5/15

Y1 - 2018/5/15

N2 - Timely determination of antimicrobial susceptibility for a bacterial infection enables precision prescription, shortens treatment time, and helps minimize the spread of antibiotic resistant infections. Current antimicrobial susceptibility testing (AST) methods often take several days and thus impede these clinical and health benefits. Here, we present an AST method by imaging freely moving bacterial cells in urine in real time and analyzing the videos with a deep learning algorithm. The deep learning algorithm determines if an antibiotic inhibits a bacterial cell by learning multiple phenotypic features of the cell without the need for defining and quantifying each feature. We apply the method to urinary tract infection, a common infection that affects millions of people, to determine the minimum inhibitory concentration of pathogens from both bacteria spiked urine and clinical infected urine samples for different antibiotics within 30 min and validate the results with the gold standard broth macrodilution method. The deep learning video microscopy-based AST holds great potential to contribute to the solution of increasing drug-resistant infections.

AB - Timely determination of antimicrobial susceptibility for a bacterial infection enables precision prescription, shortens treatment time, and helps minimize the spread of antibiotic resistant infections. Current antimicrobial susceptibility testing (AST) methods often take several days and thus impede these clinical and health benefits. Here, we present an AST method by imaging freely moving bacterial cells in urine in real time and analyzing the videos with a deep learning algorithm. The deep learning algorithm determines if an antibiotic inhibits a bacterial cell by learning multiple phenotypic features of the cell without the need for defining and quantifying each feature. We apply the method to urinary tract infection, a common infection that affects millions of people, to determine the minimum inhibitory concentration of pathogens from both bacteria spiked urine and clinical infected urine samples for different antibiotics within 30 min and validate the results with the gold standard broth macrodilution method. The deep learning video microscopy-based AST holds great potential to contribute to the solution of increasing drug-resistant infections.

UR - http://www.scopus.com/inward/record.url?scp=85046485207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046485207&partnerID=8YFLogxK

U2 - 10.1021/acs.analchem.8b01128

DO - 10.1021/acs.analchem.8b01128

M3 - Article

C2 - 29677440

AN - SCOPUS:85046485207

VL - 90

SP - 6314

EP - 6322

JO - Analytical Chemistry

JF - Analytical Chemistry

SN - 0003-2700

IS - 10

ER -